Showing 31 - 40 of 147
Persistent link: https://www.econbiz.de/10010948138
The method of Bayesian model selection for join point regression models is developed. Given a set of "K"&plus;1 join point models "M"<sub>0</sub>, "M"<sub>1</sub>, …, "M"<sub>" K"</sub> with 0, 1, …, "K" join points respec-tively, the posterior distributions of the parameters and competing models "M"<sub>"k"</sub> are computed...
Persistent link: https://www.econbiz.de/10005217072
Zellner (1975), Chaloner and Brant (1988), and Chaloner (1991) used the posterior distributions of the realized errors to define outliers in a linear model. The same concept is used here to define outliers in a state-space model. An effective approach to compute the posterior probabilities of...
Persistent link: https://www.econbiz.de/10005319288
In this paper we present a widely applicable definition of the predictive likelihood based on estimators that are either sufficient or approximately sufficient. Under regularity conditions, this predictive likelihood is shown to equal the Bayes prediction density up to terms of order O p(n-1)....
Persistent link: https://www.econbiz.de/10005319352
A mathc statistic considered by Khidr (1981) is interpreted in terms of crossings of the empirical and true distribution functions and a simpler alternate derivation of its distribution provided. This approach can also be used to obtain the distribution of a two-sample match statistic,...
Persistent link: https://www.econbiz.de/10005319828
Persistent link: https://www.econbiz.de/10005355848
The National Cancer Institute (NCI) suggests a sudden reduction in prostate cancer mortality rates, likely due to highly successful treatments and screening methods for early diagnosis. We are interested in understanding the impact of medical breakthroughs, treatments, or interventions, on the...
Persistent link: https://www.econbiz.de/10010549829
Persistent link: https://www.econbiz.de/10010722369
Persistent link: https://www.econbiz.de/10006622357
Persistent link: https://www.econbiz.de/10006631270